2 papers
cs.LG2026
The Premise Is the Problem: Exchangeability Failure in Self-Monitored Test-Time Adaptation
Weijia Han, Lisha Qu, Zhenda Li +1
Modern forecasting models are often updated after deployment so they can respond to changing data. These updates can also make predictions worse, so practical systems need a reliab…
cs.CV2026
Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-Distillation
Jianghao Wang, Ke Meng, Jian Li +7
Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computationally expensive. Token com…